[PATCH v3 10/15] KVM: arm64: Atomically update stage 2 leaf attributes in parallel walks

From: Oliver Upton <oliver.upton@linux.dev>
To: Marc Zyngier <maz@kernel.org>, James Morse <james.morse@arm.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>
Cc: linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org,
	Reiji Watanabe <reijiw@google.com>,
	Ricardo Koller <ricarkol@google.com>,
	David Matlack <dmatlack@google.com>,
	Quentin Perret <qperret@google.com>,
	Ben Gardon <bgardon@google.com>, Gavin Shan <gshan@redhat.com>,
	Peter Xu <peterx@redhat.com>, Will Deacon <will@kernel.org>,
	Sean Christopherson <seanjc@google.com>,
	kvmarm@lists.linux.dev, Oliver Upton <oliver.upton@linux.dev>
Subject: [PATCH v3 10/15] KVM: arm64: Atomically update stage 2 leaf attributes in parallel walks
Date: Thu, 27 Oct 2022 22:22:08 +0000	[thread overview]
Message-ID: <20221027222208.1684910-1-oliver.upton@linux.dev> (raw)
In-Reply-To: <20221027221752.1683510-1-oliver.upton@linux.dev>

The stage2 attr walker is already used for parallel walks. Since commit
f783ef1c0e82 ("KVM: arm64: Add fast path to handle permission relaxation
during dirty logging"), KVM acquires the read lock when
write-unprotecting a PTE. However, the walker only uses a simple store
to update the PTE. This is safe as the only possible race is with
hardware updates to the access flag, which is benign.

However, a subsequent change to KVM will allow more changes to the stage
2 page tables to be done in parallel. Prepare the stage 2 attribute
walker by performing atomic updates to the PTE when walking in parallel.

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_pgtable.h |  8 +++++++
 arch/arm64/kvm/hyp/pgtable.c         | 31 ++++++++++++++++++++--------
 2 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index f35e7d4d73f1..7634b6964779 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -243,11 +243,14 @@ struct kvm_pgtable {
  *					children.
  * @KVM_PGTABLE_WALK_TABLE_POST:	Visit table entries after their
  *					children.
+ * @KVM_PGTABLE_WALK_SHARED:		Indicates the page-tables may be shared
+ *					with other software walkers.
  */
 enum kvm_pgtable_walk_flags {
 	KVM_PGTABLE_WALK_LEAF			= BIT(0),
 	KVM_PGTABLE_WALK_TABLE_PRE		= BIT(1),
 	KVM_PGTABLE_WALK_TABLE_POST		= BIT(2),
+	KVM_PGTABLE_WALK_SHARED			= BIT(3),
 };
 
 struct kvm_pgtable_visit_ctx {
@@ -264,6 +267,11 @@ struct kvm_pgtable_visit_ctx {
 typedef int (*kvm_pgtable_visitor_fn_t)(const struct kvm_pgtable_visit_ctx *ctx,
 					enum kvm_pgtable_walk_flags visit);
 
+static inline bool kvm_pgtable_walk_shared(const struct kvm_pgtable_visit_ctx *ctx)
+{
+	return ctx->flags & KVM_PGTABLE_WALK_SHARED;
+}
+
 /**
  * struct kvm_pgtable_walker - Hook into a page-table walk.
  * @cb:		Callback function to invoke during the walk.
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 5bab932aeaec..7c0dd58544b0 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -185,7 +185,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 				      kvm_pteref_t pteref, u32 level)
 {
 	enum kvm_pgtable_walk_flags flags = data->walker->flags;
-	kvm_pte_t *ptep = kvm_dereference_pteref(pteref, false);
+	kvm_pte_t *ptep = kvm_dereference_pteref(pteref, flags & KVM_PGTABLE_WALK_SHARED);
 	struct kvm_pgtable_visit_ctx ctx = {
 		.ptep	= ptep,
 		.old	= READ_ONCE(*ptep),
@@ -675,6 +675,16 @@ static bool stage2_pte_is_counted(kvm_pte_t pte)
 	return !!pte;
 }
 
+static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new)
+{
+	if (!kvm_pgtable_walk_shared(ctx)) {
+		WRITE_ONCE(*ctx->ptep, new);
+		return true;
+	}
+
+	return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old;
+}
+
 static void stage2_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu,
 			   struct kvm_pgtable_mm_ops *mm_ops)
 {
@@ -986,7 +996,9 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
 		    stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old))
 			mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops),
 						  kvm_granule_size(ctx->level));
-		WRITE_ONCE(*ctx->ptep, pte);
+
+		if (!stage2_try_set_pte(ctx, pte))
+			return -EAGAIN;
 	}
 
 	return 0;
@@ -995,7 +1007,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
 static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 				    u64 size, kvm_pte_t attr_set,
 				    kvm_pte_t attr_clr, kvm_pte_t *orig_pte,
-				    u32 *level)
+				    u32 *level, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI;
@@ -1006,7 +1018,7 @@ static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_attr_walker,
 		.arg		= &data,
-		.flags		= KVM_PGTABLE_WALK_LEAF,
+		.flags		= flags | KVM_PGTABLE_WALK_LEAF,
 	};
 
 	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
@@ -1025,14 +1037,14 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
 	return stage2_update_leaf_attrs(pgt, addr, size, 0,
 					KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W,
-					NULL, NULL);
+					NULL, NULL, 0);
 }
 
 kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
 	stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
-				 &pte, NULL);
+				 &pte, NULL, 0);
 	dsb(ishst);
 	return pte;
 }
@@ -1041,7 +1053,7 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
 	stage2_update_leaf_attrs(pgt, addr, 1, 0, KVM_PTE_LEAF_ATTR_LO_S2_AF,
-				 &pte, NULL);
+				 &pte, NULL, 0);
 	/*
 	 * "But where's the TLBI?!", you scream.
 	 * "Over in the core code", I sigh.
@@ -1054,7 +1066,7 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
 bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL);
+	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL, 0);
 	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
 }
 
@@ -1077,7 +1089,8 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 	if (prot & KVM_PGTABLE_PROT_X)
 		clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
 
-	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level);
+	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level,
+				       KVM_PGTABLE_WALK_SHARED);
 	if (!ret)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level);
 	return ret;
-- 
2.38.1.273.g43a17bfeac-goog

